We present an algorithm for reconstruction of a probabilistic deterministic finite automaton
(PDFA) from a given black-box language model, such as a recurrent neural network (RNN) …

Understanding how a learned black box works is of crucial interest for the future of Machine
Learning. In this paper, we pioneer the question of the global interpretability of learned black …

Recent work on semantic parsing has shown that seq2seq models find compositional
generalization challenging. Several strategies have been proposed to mitigate this …

This paper is an attempt to bridge the gap between deep learning and grammatical
inference. Indeed, it provides an algorithm to extract a (stochastic) formal language from any …

In this paper, we present connections between three models used in different research
fields: weighted finite automata (WFA) from formal languages and linguistics, recurrent …

We compare a classical CNN architecture for sequence classification involving several
convolutional and max-pooling layers against a simple model based on weighted finite state …

Spectral models for learning weighted non-deterministic automata have nice theoretical and
algorithmic properties. Despite this, it has been challenging to obtain competitive results in …

Sequential data refers to information that is ordered into sequences, such as time series,
natural language, and DNA sequences [Sammut and Webb, 2010]. This type of data is …

This paper deals with the maximum cardinality matching (MCM) problem. The augmenting
path technique is well known in MCM. MCM is obtained by $ O ({\sqrt {n}} m) $ time …

Sequence models, in particular, language models are fundamental building blocks of
downstream applications including speech recognition, speech synthesis, information …